{"id":"https://openalex.org/W7160263723","doi":"https://doi.org/10.1109/wacv61042.2026.00384","title":"CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding","display_name":"CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160263723","doi":"https://doi.org/10.1109/wacv61042.2026.00384"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001096493","display_name":"Fevziye \u0130rem Eyiokur","orcid":"https://orcid.org/0000-0001-5754-5405"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fevziye Irem Eyiokur","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055264805","display_name":"Do\u011fucan Yaman","orcid":"https://orcid.org/0000-0002-5047-295X"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dogucan Yaman","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009982931","display_name":"Haz\u0131m Kemal Ekenel","orcid":"https://orcid.org/0000-0003-3697-8548"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Haz\u0131m Kemal Ekenel","raw_affiliation_strings":["Istanbul Technical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istanbul Technical University","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023053982","display_name":"Alexander Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Waibel","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3939","last_page":"3950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.23240000009536743,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.23240000009536743,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.21209999918937683,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.04650000110268593,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.491100013256073},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2879999876022339},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.27160000801086426},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24709999561309814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5813000202178955},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453900009393692},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24709999561309814},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.24310000240802765},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.24089999496936798}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.5712855458259583,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1553305517","https://openalex.org/W1970320256","https://openalex.org/W1993704986","https://openalex.org/W2000588622","https://openalex.org/W2012992404","https://openalex.org/W2045284424","https://openalex.org/W2059916030","https://openalex.org/W2076454503","https://openalex.org/W2102605133","https://openalex.org/W2118242609","https://openalex.org/W2135002326","https://openalex.org/W2136451251","https://openalex.org/W2136492166","https://openalex.org/W2157725521","https://openalex.org/W2166790283","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2559085405","https://openalex.org/W2947543340","https://openalex.org/W2962730651","https://openalex.org/W2963037989","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2984401364","https://openalex.org/W2987734933","https://openalex.org/W3022565501","https://openalex.org/W3096609285","https://openalex.org/W3110435696","https://openalex.org/W3112077297","https://openalex.org/W3149839747","https://openalex.org/W3159619744","https://openalex.org/W3173859428","https://openalex.org/W3197501724","https://openalex.org/W3210853113","https://openalex.org/W4214627427","https://openalex.org/W4292793996","https://openalex.org/W4293253477","https://openalex.org/W4293526428","https://openalex.org/W4312312588","https://openalex.org/W4312795113","https://openalex.org/W4321353636","https://openalex.org/W4385245566","https://openalex.org/W4386790226","https://openalex.org/W4388624021","https://openalex.org/W4390189653","https://openalex.org/W4390872917","https://openalex.org/W4390873312","https://openalex.org/W4390874396","https://openalex.org/W4393149032","https://openalex.org/W4401043452","https://openalex.org/W4402715878","https://openalex.org/W4402716047","https://openalex.org/W4402781286","https://openalex.org/W4402916273","https://openalex.org/W4404004697","https://openalex.org/W4404612908","https://openalex.org/W4411638696","https://openalex.org/W4413146564","https://openalex.org/W4413147571","https://openalex.org/W4414197327","https://openalex.org/W4415795406","https://openalex.org/W4416749638","https://openalex.org/W7133184875","https://openalex.org/W7133193647"],"related_works":[],"abstract_inverted_index":{"We":[0,46,99,151,164],"address":[1,77],"Embodied":[2],"Reference":[3],"Understanding,":[4],"the":[5,9,14,51,56,67,89,93,96,122,137],"task":[6],"of":[7,106],"predicting":[8],"object":[10,156],"a":[11,71,81,101,116,144],"person":[12],"in":[13,59],"scene":[15,33],"refers":[16],"to":[17,40,114,124,127,160],"through":[18],"pointing":[19,30,128],"gesture":[20],"and":[21,32,92,109,179,184,191],"language.":[22],"This":[23],"requires":[24],"multimodal":[25],"reasoning":[26],"over":[27],"text,":[28],"visual":[29,43],"cues,":[31],"context,":[34],"yet":[35],"existing":[36],"methods":[37],"often":[38,53],"fail":[39],"fully":[41],"exploit":[42],"disambiguation":[44],"signals.":[45],"also":[47],"observe":[48],"that":[49,120],"while":[50],"referent":[52,162],"aligns":[54,63],"with":[55,66],"head-to-fingertip":[57,90],"direction,":[58,69],"many":[60],"cases":[61],"it":[62],"more":[64],"closely":[65],"wrist-to-fingertip":[68,97],"making":[70],"single-line":[72],"assumption":[73],"overly":[74],"limiting.":[75],"To":[76,130],"this,":[78],"we":[79,135],"propose":[80],"dual-model":[82],"framework,":[83],"where":[84],"one":[85],"model":[86,123],"learns":[87],"from":[88,95],"direction":[91],"other":[94],"direction.":[98],"introduce":[100],"Gaussian":[102],"ray":[103],"heatmap":[104],"representation":[105],"these":[107],"lines":[108],"use":[110],"them":[111],"as":[112],"input":[113],"provide":[115],"strong":[117],"supervisory":[118],"signal":[119],"encourages":[121],"better":[125],"attend":[126],"cues.":[129],"fuse":[131],"their":[132],"complementary":[133],"strengths,":[134],"present":[136],"CLIP-Aware":[138],"Pointing":[139],"Ensemble":[140],"module,":[141],"which":[142],"performs":[143],"hybrid":[145],"ensemble":[146],"guided":[147],"by":[148],"CLIP":[149,178],"features.":[150],"further":[152],"incorporate":[153],"an":[154],"auxiliary":[155],"center":[157],"prediction":[158],"head":[159],"enhance":[161],"localization.":[163],"validate":[165],"our":[166],"approach":[167],"on":[168,188],"YouRefIt,":[169],"achieving":[170],"75.0":[171],"mAP":[172],"at":[173],"0.25":[174],"IoU,":[175],"alongside":[176],"state-of-the-art":[177],"C<inf":[180],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[181],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">D</inf>":[182],"scores,":[183],"demonstrate":[185],"its":[186],"generality":[187],"unseen":[189],"CAESAR":[190],"ISL":[192],"Pointing,":[193],"showing":[194],"robust":[195],"performance":[196],"across":[197],"benchmarks.":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}